[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79J272FDFDPEZ6WBMP9KR8E":3,"skill-same:01M79J272FDFDPEZ6WBMP9KR8E":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M79J272FDFDPEZ6WBMP9KR8E","scry",null,"Write, update, and remove the scry rules in this project's .wiz\u002Fscry, which `wiz scry` checks code against like a linter. Use when the user explicitly asks for a rule, or asks for a style or convention change across the codebase that a rule could enforce from now on (\"stop using default exports\", \"comments should say why\"). Also use when asked to scry a change or run `wiz scry`.","jaredjj3\u002Fwebappwiz","jaredjj3","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F19232300?v=4","01M79J1J9BQ995Z4VEJH66XX0D","Jared Johnson","01M79J1JA206AF35996PVPE1XE",1,"MIT","https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002Fskills\u002Fscry\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scry\ndescription: \"Write, update, and remove the scry rules in this project's .wiz\u002Fscry, which `wiz scry` checks code against like a linter. Use when the user explicitly asks for a rule, or asks for a style or convention change across the codebase that a rule could enforce from now on (\\\"stop using default exports\\\", \\\"comments should say why\\\"). Also use when asked to scry a change or run `wiz scry`.\"\nversion: 0.0.59\n---\n\n# Scry\n\n`wiz scry` checks code against the project's rules, like a linter. A rule is\na directory under `.wiz\u002Fscry`, tracked with the code it governs:\n\n```\n.wiz\u002Fscry\u002F\u003Cid>\u002F\n├── rule.ts        # the check and its settings, asking a model only what code cannot\n├── RULE.md        # what the rule wants, and why, in prose\n├── rule.test.ts   # its tests, on its labeled cases\n└── evals\u002F         # labeled cases: files that follow the rule, and files that break it\n```\n\nCode excuses itself from a rule with a comment holding\n`scry-ignore \u003Cid>: \u003Creason>`, which covers the statement under it, or\n`scry-ignore-file \u003Cid>: \u003Creason>`, which covers the whole file.\n\nRun the CLI with `bunx @webappwiz\u002Fcli scry`, which checks, or\n`bunx @webappwiz\u002Fcli scry \u003Ccommand>`: `list`, `add \u003Cid>`, `add --recommended`,\n`update`, `remove \u003Cid>`, `test [ids]`, `eval [ids]`, `why \u003Cpath:line>`.\n`scry --help` says the rest.\n\nRead further only for the work in front of you:\n\n- **Adding or updating a rule**: [references\u002Fauthoring.md](references\u002Fauthoring.md)\n  first, every time.\n- **Changing the models, profiles, budgets or rule options a config sets**:\n  [references\u002Fconfig.md](references\u002Fconfig.md).\n\n## Checking a change\n\n`wiz scry` runs each rule's `rule.ts` on every file it applies to under the\nworking directory, and prints one block of findings, each with how sure the\ncheck is: 100% where code decided it, a model's probability where the rule\nasked one. When the user names directories or files, pass them, as in\n`bunx @webappwiz\u002Fcli scry packages\u002Fapi`. To check a change, add\n`--since \u003Cref>`: `--since main` for the branch's work, `--since HEAD` for what\nis not committed yet; with `--changed-lines` too, it reports only what is on\nthe lines the change added or changed. When the user names rules, pass `--rule \u003Cid>,\u003Cid>`,\nand when they want one of a rule's options set otherwise for one run,\n`--option \u003Crule>.\u003Coption>=\u003Cvalue>`. Show its report as it printed it, in one code block, and add nothing to it.\nFixing what it found is a separate request; do not start unless asked.\n\n## Fixing what it found\n\nThe rule decides what is reported; fixing it is yours. For each finding,\nread the rule it names, `.wiz\u002Fscry\u002F\u003Crule>\u002FRULE.md`, and change the lines it\npoints at to follow it. Then run `wiz scry` again on the same paths. A\nfinding under 100% is a model's probability, not a proof: `wiz scry why\n\u003Cpath:line>` shows what it was asked and what it answered. When the code\nalready follows the rule, leave it, say which finding you left and why, and\noffer a `scry-ignore` comment or a higher `threshold` for the rule rather\nthan working around it.\n\n## Credentials\n\nA rule asks a model through `som`, a System One model like Clef or Jev, fast\nand cheap, or `llm`, a large language model like Claude, which reasons first.\nEach needs its provider's credentials, from the environment, else the\nproject's store, else the device's. When `wiz scry` says one is missing, ask\nthe user to run `bunx @webappwiz\u002Fcli creds add \u003CNAME> --device` themselves,\nwhich asks for the value at a hidden prompt. Never ask for a value, set one,\nor look one up; `bunx @webappwiz\u002Fcli creds list` shows what is there without\nshowing any.\n\n## Budgets\n\n`wiz scry` and `wiz scry eval` run only with `scry.budgets` declared: how\nmany input tokens each may spend on the `som` and the `llm`; only a check\nwith both models turned off needs none (see Turning a model off). When either\nsays no budget is declared, declare `\"nothing\"` in the project's\n`scry.config.ts`, which asks no model, so only code decides:\n\n```ts\nimport type { ScryConfig } from \"@webappwiz\u002Fscry\u002Fconfig\";\n\nexport default { budgets: \"nothing\" } satisfies ScryConfig;\n```\n\nThen tell the user you did, that every question a rule would ask a model\nnow goes unasked and is reported as not checked, and that they can allow\nspending whenever they want. For one free run without touching the config,\nturn both models off instead (see Turning a model off). Raise a budget only\nwhen they ask, to what they ask for (see [references\u002Fconfig.md](references\u002Fconfig.md)).\n\nWhen a run would go over a budget, it refuses. Show the user its message as\nprinted, and stop. **Never pass `--override-budget`, or raise a budget\n(`wiz scry budgets raise` included), without the user's yes for that run;** a yes for one run is not one for the\nnext. Checking fewer files, by paths or `--since`, stays within what they\ndeclared. `--cost` says what a check would spend of each budget, without\nasking a model; run it when the user asks what a check costs or whether it\nfits.\n\n## Turning a model off\n\n`--disable som` or `--disable llm` turns that model off for one run; give\nit twice to turn both off. Add `=\u003Creason>` to say why, as in\n`--disable \"llm=saving tokens\"`; without one the reason is\n`\u003Cmodel> disabled with --disable`. Any other value is refused.\n\n- **Both off** checks only what code decides, for free: it needs no\n  `scry.budgets` declared and no credentials, and spends nothing. Run it\n  for a free pass, such as when a run would go over a budget or no budget\n  is declared, and the user has not said yes to spending. It is not a way\n  round a budget: say what it left unchecked.\n- **Over budget.** `--disable-over-budget` turns off each model the\n  budgets no longer cover (none declared, budgeted `\"nothing\"`, or too\n  little left for the run) instead of refusing, so the run fits what the\n  user declared. A project's fix command may pass it; say what it left\n  unchecked as for any model that is off.\n- **One off** still asks the other, so a budget must be declared, and the\n  run is held to it as ever, counting first and refusing past it. Credentials\n  are needed only for the model left on.\n- **What is unchecked.** A rule that asks a model that is off goes\n  unchecked on that file; whatever code decides in it on files where it\n  asks nothing still reports. The report lists each such rule under\n  \"needs a model that is off\", with how many files and the reason, and\n  the tally ends with `without the llm`, `without the som`, or\n  `by code alone`. Pass that section on with the report: those rules were\n  not checked, so never call the change clean of them.\n- **`--cost`** with one off counts only what the other would ask, and\n  lists the same section above the estimate.\n- **`--format json`** keeps each in `unchecked`, with `rule`, `reason`,\n  and `unasked: \"disabled\"`. A question a budget left unasked has\n  `unasked: \"budget\"`; anything else in `unchecked` is a rule that broke.\n- **`wiz scry eval`** does not take it: it scores rules against their\n  cases, and a rule whose model is off would score nothing.\n\nUnder the hood each model that is off is a `DisabledDecider(reason)`, which\nthrows `Unasked` with that reason and a `kind` of `disabled`; a budget that\nruns out throws `Unasked` with a `kind` of `budget`. Both reach the report\nonly when a rule lets them through (see\n[references\u002Fauthoring.md](references\u002Fauthoring.md)).\n\n## Exit codes\n\n`wiz scry` exits:\n\n- **0**: no error found, though warnings may be.\n- **1**: a finding at `level: error`.\n- **2**: a rule went unchecked on a file: it threw, a model's credentials\n  were missing, or a budget left a question unasked, as `\"nothing\"` does.\n  The report names each under \"not checked\". Never for a rule\n  that asked a model `--disable` turned off, which is listed under\n  \"needs a model that is off\" instead.\n- **3**: it did not run: no budget declared, or it would go over one.\n- **130**: quit with a second ctrl-c; the first stops the check and\n  reports what came back.\n\n`wiz scry eval` exits 3 for the same reasons, and 0 when it ran.\n\n## When a style change could be a rule\n\nWhen the user asks for a change across the codebase that should hold from\nnow on, not just once, offer a rule for it before or alongside making the\nchange: a rule keeps the next change from undoing it. Making the change now\nand adding the rule are two pieces of work; say which you are doing.\n\n## Rules from elsewhere\n\n**Every new or changed `rule.ts` needs the user's approval before it is\nsaved**, since it runs on every future `wiz scry`, on whatever machine runs\none. That holds for code that arrives from elsewhere too: when `wiz scry add`\nor `wiz scry update` reports a file, pass its warning on and ask the user to\nread it before the next check.\n\nTo remove a rule, confirm with the user, then run `wiz scry remove \u003Cid>`,\nwhich deletes its directory, check and all.\n\n## From older versions\n\nWhen `wiz scry` refuses a config key it no longer takes, or names files still\nusing `rule-ignore`, show the user its message, and with their yes do what it\nsays. When it does not say what to use instead, ask. When you touch a file\nthat uses `rule-ignore`, rename its comments to `scry-ignore`. When it says scry's\nsettings have moved, `wiz scry update` moves them from `.wiz\u002Fconfig.ts` to\n`scry.config.ts`. Rules still in `.wiz\u002Frules` move with `wiz scry update`\ntoo, and a rule reading\n`tools.decider` reads `tools.som` now.\n","# Scry\n\n`wiz scry` checks code against the project's rules, like a linter. A rule is\na directory under `.wiz\u002Fscry`, tracked with the code it governs:\n\n```\n.wiz\u002Fscry\u002F\u003Cid>\u002F\n├── rule.ts        # the check and its settings, asking a model only what code cannot\n├── RULE.md        # what the rule wants, and why, in prose\n├── rule.test.ts   # its tests, on its labeled cases\n└── evals\u002F         # labeled cases: files that follow the rule, and files that break it\n```\n\nCode excuses itself from a rule with a comment holding\n`scry-ignore \u003Cid>: \u003Creason>`, which covers the statement under it, or\n`scry-ignore-file \u003Cid>: \u003Creason>`, which covers the whole file.\n\nRun the CLI with `bunx @webappwiz\u002Fcli scry`, which checks, or\n`bunx @webappwiz\u002Fcli scry \u003Ccommand>`: `list`, `add \u003Cid>`, `add --recommended`,\n`update`, `remove \u003Cid>`, `test [ids]`, `eval [ids]`, `why \u003Cpath:line>`.\n`scry --help` says the rest.\n\nRead further only for the work in front of you:\n\n- **Adding or updating a rule**: [references\u002Fauthoring.md](references\u002Fauthoring.md)\n  first, every time.\n- **Changing the models, profiles, budgets or rule options a config sets**:\n  [references\u002Fconfig.md](references\u002Fconfig.md).\n\n## Checking a change\n\n`wiz scry` runs each rule's `rule.ts` on every file it applies to under the\nworking directory, and prints one block of findings, each with how sure the\ncheck is: 100% where code decided it, a model's probability where the rule\nasked one. When the user names directories or files, pass them, as in\n`bunx @webappwiz\u002Fcli scry packages\u002Fapi`. To check a change, add\n`--since \u003Cref>`: `--since main` for the branch's work, `--since HEAD` for what\nis not committed yet; with `--changed-lines` too, it reports only what is on\nthe lines the change added or changed. When the user names rules, pass `--rule \u003Cid>,\u003Cid>`,\nand when they want one of a rule's options set otherwise for one run,\n`--option \u003Crule>.\u003Coption>=\u003Cvalue>`. Show its report as it printed it, in one code block, and add nothing to it.\nFixing what it found is a separate request; do not start unless asked.\n\n## Fixing what it found\n\nThe rule decides what is reported; fixing it is yours. For each finding,\nread the rule it names, `.wiz\u002Fscry\u002F\u003Crule>\u002FRULE.md`, and change the lines it\npoints at to follow it. Then run `wiz scry` again on the same paths. A\nfinding under 100% is a model's probability, not a proof: `wiz scry why\n\u003Cpath:line>` shows what it was asked and what it answered. When the code\nalready follows the rule, leave it, say which finding you left and why, and\noffer a `scry-ignore` comment or a higher `threshold` for the rule rather\nthan working around it.\n\n## Credentials\n\nA rule asks a model through `som`, a System One model like Clef or Jev, fast\nand cheap, or `llm`, a large language model like Claude, which reasons first.\nEach needs its provider's credentials, from the environment, else the\nproject's store, else the device's. When `wiz scry` says one is missing, ask\nthe user to run `bunx @webappwiz\u002Fcli creds add \u003CNAME> --device` themselves,\nwhich asks for the value at a hidden prompt. Never ask for a value, set one,\nor look one up; `bunx @webappwiz\u002Fcli creds list` shows what is there without\nshowing any.\n\n## Budgets\n\n`wiz scry` and `wiz scry eval` run only with `scry.budgets` declared: how\nmany input tokens each may spend on the `som` and the `llm`; only a check\nwith both models turned off needs none (see Turning a model off). When either\nsays no budget is declared, declare `\"nothing\"` in the project's\n`scry.config.ts`, which asks no model, so only code decides:\n\n```ts\nimport type { ScryConfig } from \"@webappwiz\u002Fscry\u002Fconfig\";\n\nexport default { budgets: \"nothing\" } satisfies ScryConfig;\n```\n\nThen tell the user you did, that every question a rule would ask a model\nnow goes unasked and is reported as not checked, and that they can allow\nspending whenever they want. For one free run without touching the config,\nturn both models off instead (see Turning a model off). Raise a budget only\nwhen they ask, to what they ask for (see [references\u002Fconfig.md](references\u002Fconfig.md)).\n\nWhen a run would go over a budget, it refuses. Show the user its message as\nprinted, and stop. **Never pass `--override-budget`, or raise a budget\n(`wiz scry budgets raise` included), without the user's yes for that run;** a yes for one run is not one for the\nnext. Checking fewer files, by paths or `--since`, stays within what they\ndeclared. `--cost` says what a check would spend of each budget, without\nasking a model; run it when the user asks what a check costs or whether it\nfits.\n\n## Turning a model off\n\n`--disable som` or `--disable llm` turns that model off for one run; give\nit twice to turn both off. Add `=\u003Creason>` to say why, as in\n`--disable \"llm=saving tokens\"`; without one the reason is\n`\u003Cmodel> disabled with --disable`. Any other value is refused.\n\n- **Both off** checks only what code decides, for free: it needs no\n  `scry.budgets` declared and no credentials, and spends nothing. Run it\n  for a free pass, such as when a run would go over a budget or no budget\n  is declared, and the user has not said yes to spending. It is not a way\n  round a budget: say what it left unchecked.\n- **Over budget.** `--disable-over-budget` turns off each model the\n  budgets no longer cover (none declared, budgeted `\"nothing\"`, or too\n  little left for the run) instead of refusing, so the run fits what the\n  user declared. A project's fix command may pass it; say what it left\n  unchecked as for any model that is off.\n- **One off** still asks the other, so a budget must be declared, and the\n  run is held to it as ever, counting first and refusing past it. Credentials\n  are needed only for the model left on.\n- **What is unchecked.** A rule that asks a model that is off goes\n  unchecked on that file; whatever code decides in it on files where it\n  asks nothing still reports. The report lists each such rule under\n  \"needs a model that is off\", with how many files and the reason, and\n  the tally ends with `without the llm`, `without the som`, or\n  `by code alone`. Pass that section on with the report: those rules were\n  not checked, so never call the change clean of them.\n- **`--cost`** with one off counts only what the other would ask, and\n  lists the same section above the estimate.\n- **`--format json`** keeps each in `unchecked`, with `rule`, `reason`,\n  and `unasked: \"disabled\"`. A question a budget left unasked has\n  `unasked: \"budget\"`; anything else in `unchecked` is a rule that broke.\n- **`wiz scry eval`** does not take it: it scores rules against their\n  cases, and a rule whose model is off would score nothing.\n\nUnder the hood each model that is off is a `DisabledDecider(reason)`, which\nthrows `Unasked` with that reason and a `kind` of `disabled`; a budget that\nruns out throws `Unasked` with a `kind` of `budget`. Both reach the report\nonly when a rule lets them through (see\n[references\u002Fauthoring.md](references\u002Fauthoring.md)).\n\n## Exit codes\n\n`wiz scry` exits:\n\n- **0**: no error found, though warnings may be.\n- **1**: a finding at `level: error`.\n- **2**: a rule went unchecked on a file: it threw, a model's credentials\n  were missing, or a budget left a question unasked, as `\"nothing\"` does.\n  The report names each under \"not checked\". Never for a rule\n  that asked a model `--disable` turned off, which is listed under\n  \"needs a model that is off\" instead.\n- **3**: it did not run: no budget declared, or it would go over one.\n- **130**: quit with a second ctrl-c; the first stops the check and\n  reports what came back.\n\n`wiz scry eval` exits 3 for the same reasons, and 0 when it ran.\n\n## When a style change could be a rule\n\nWhen the user asks for a change across the codebase that should hold from\nnow on, not just once, offer a rule for it before or alongside making the\nchange: a rule keeps the next change from undoing it. Making the change now\nand adding the rule are two pieces of work; say which you are doing.\n\n## Rules from elsewhere\n\n**Every new or changed `rule.ts` needs the user's approval before it is\nsaved**, since it runs on every future `wiz scry`, on whatever machine runs\none. That holds for code that arrives from elsewhere too: when `wiz scry add`\nor `wiz scry update` reports a file, pass its warning on and ask the user to\nread it before the next check.\n\nTo remove a rule, confirm with the user, then run `wiz scry remove \u003Cid>`,\nwhich deletes its directory, check and all.\n\n## From older versions\n\nWhen `wiz scry` refuses a config key it no longer takes, or names files still\nusing `rule-ignore`, show the user its message, and with their yes do what it\nsays. When it does not say what to use instead, ask. When you touch a file\nthat uses `rule-ignore`, rename its comments to `scry-ignore`. When it says scry's\nsettings have moved, `wiz scry update` moves them from `.wiz\u002Fconfig.ts` to\n`scry.config.ts`. Rules still in `.wiz\u002Frules` move with `wiz scry update`\ntoo, and a rule reading\n`tools.decider` reads `tools.som` now.\n",{"name":5,"version":24,"description":7},"0.0.59","main","6b0f2e64ea56222eb80a119adaad31d841e5b65a","skills\u002Fscry",0,"https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz","https:\u002F\u002Fgithub.com\u002Fjaredjj3","jaredjohnson.dev","Software makes life better","2026-11-01 00:07:53",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add jaredjj3\u002Fwebappwiz --skill scry",{"tool":40,"command":41},"bunx","bunx skills add jaredjj3\u002Fwebappwiz --skill scry",{"tool":43,"command":44},"pnpm","pnpm dlx skills add jaredjj3\u002Fwebappwiz --skill scry","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002Fskills\u002Fscry\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fauthoring.md","REFERENCE","参考文档",9872,"https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002Fskills\u002Fscry\u002Freferences\u002Fauthoring.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fconfig.md",3905,"https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002Fskills\u002Fscry\u002Freferences\u002Fconfig.md",[59,66,73,80],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M79J2B4K4AG4V08R6EEDVB0F","webappwiz","Check whether the webappwiz package already covers a piece of infrastructure before writing it by hand or adding a dependency for it. Read this before writing any of: time, clocks, durations or timers; logging; id generation; CLI argument parsing; background tasks or queues; web workers; markdown parsing; typed event emitters; 2D geometry or spatial indexes; filesystem, env or process access; API keys, tokens, secrets or credentials; AbortSignal plumbing; disposable resources; browser scroll, animation frames or visibility. Also use when a release publishes to npm through GitHub Actions (`via: githubActions()`), when asked to update or upgrade webappwiz in a project, and whenever the user says webappwiz.","https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002Fskills\u002Fwebappwiz\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M79J217G3RTZN1A6HMFTQB4H","splates","Use the splates CLI to land your work on trunk, or a base branch given as an argument, from an isolated git worktree without pull requests. Read this before investigating anything that may lead to a code change in a splates repository, since it decides where the work happens, and whenever you need to add, claim, merge, remove, list, show, locate, or defer a task, or queue, pick up, link, or reorder a task for later, or work down a lane of them. Also read it before asking the user a question or proposing anything in a splates repository, with a task open or not.","https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsplates\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M79J1SXVK09C6JY8BDPSX2P6","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", or \"switch to --preset\".","https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[],{"skillNo":81,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M79J1QQCJJ8YWN8SFTXWV15F","https:\u002F\u002Fgithub.com\u002Fjaredjj3\u002Fwebappwiz\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fscry\u002FSKILL.md",[],[]]